Estimation of density log and sonic log using artificial intelligence: an example from the Perth Basin, Australia

Compressional (P-wave) and shear (S-wave) velocities are used to estimate the dynamic geomechanical properties including: Poisson’s ratio, Young’s modulus, and Lame parameters. These parameters are mainly used in estimating the static properties of the formation rocks as well as the in situ stresses. The sonic logs are not always available, epically for old wellbores. Also, in several occasions when the sonic logs are available, missing sections found in the well logs might affect the analysis results. To the authors’ knowledge, there is no single straightforward correlation that can be used to accurately estimate both P- and S-wave travel times directly from the well log data. Most of the existing correlations use the P-wave velocity to measure the S-wave velocity. The main purpose of this study is to develop accurate and simple empirical models using wireline log data (bulk density, gamma ray, and neutron porosity) to predict the sonic travel times (P-wave and S-wave). These wireline logs are slandered wireline log data that are commonly recorded in most of the wells. Three robust artificial intelligence techniques, namely: support vector machine (SVM), artificial neural network (ANN), and adaptive neurofuzzy interference systems (ANFIS), were employed and compared based on their prediction performance. Ultimately, using the weights and biases of optimized ANN model, a simple generalized empirical correlation is derived that can be used without the need of costly commercial software’s to run the AI models. The obtained results showed that ANN, ANFIS, and SVM can be used to estimate P-wave and S-wave travel times. ANN outperformed the ANFIS and SVM by yielding the lowest average absolute percentage error (AAPE) and the highest coefficient of determination $$\left( R^{2}\right) $$ for predicting P-wave and S-wave travel times. ANN model could predict the P-wave and S-wave travel times from wireline log data with high accuracy giving $$R^{2}$$ of 0.98 when compared to actual field data. In addition, the developed empirical correlations prediction completely matched the ANNs prediction. The AAPE of the predicted P and S-waves travel times was less than 5%. The developed correlations are very accurate and can help geomechanical engineers to determine the dynamic geomechanical properties (Poisson’s ratio and Young’s modulus) and propose any operation in case where sonic logs are missing.

The disruption has been occurring in financial services. Rethinking new strategy of banking is needed to make a sustainable competitive advantage innovation in organizations. The four types of business strategy for banks are prospector, analyzer, defender, and reactor. Studies mentioned that formulating strategy is very costly, time consuming, and comprehensive analysis. The banks have to get rid of execution time inefficiency, lack of flexibility, and lack of ability to present several scenarios in the dynamic business environment. The purpose of this study is to present an integrated intelligence algorithm for estimating strategic resources of the bank strategy in Indonesia. The algorithm has two basic modules which are artificial neural network (ANN) and analytical hierarchy process (AHP). ANN is utilized as an inductive algorithm in discovering predictive strategy of the bank and used to explain the strategic resources which improved in forward. AHP has the capability to handle multi-level decision-making structure with use of expert judgments in pairwise comparison process. AHP is used to measure the weight of the resources and the score is used to determine the strategy. The empirical results indicate that ANN and AHP integration is proved to predict the business strategy of the bank. The strategy choice appropriate with the condition of bank's resources. This framework can be implemented to help banker for the decision making in bank operation. Keywords: business strategy, ANN, AHP, resources

Concrete compressive strength is recognized as one of the most important mechanical properties of concrete and one of the most significant mechanical properties in determining the quality of the produced concrete. Since the traditional procedures of determining the compressive strength of concrete require time and cost, scholars have always been looking for new methods to replace them with existing traditional methods. In this paper, soft computing methods are investigated for determining the compressive strength of concrete. To be specific, 150 different concrete specimens with various mix design parameters have been built in the laboratory, and the compressive strength of them have been measured after 28 days of curing in the water. Five different concrete mix parameters, (i.e., cement, water to cement ratio, gravel, sand, and microsilica) were considered as input variables. In addition, two soft computing techniques have been used in this study which are Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference (ANFIS) System. Results have shown that both of ANN and ANFIS models are successful models for predicting the compressive strength of concrete. Also, results have shown that ANFIS is more capable than ANN in predicting the compressive strength of concrete.

The primary objective of Short-Term Load Forecasting, often known as STLF, is to forecast load with a lead time of anything from one hour to seven days. In this study, we suggest the use of AI approaches for short-term load forecasting. Some examples of these techniques are artificial neural networks (ANN) and wavelet neural networks (WNN) (STLF). A reliable prediction makes the challenge of managing generation and load much more manageable. The ANN and WNN algorithms are used in order to calculate the STLF for the next day. The comparison between the two approaches as well as their performance is outlined, and the normalized MAPE error for one day ahead is shown in the article as well. In addition to this, the Validation is performed on the TNEB testing system. This study provided an application of AI techniques, specifically ANN and WNN, for STLF applications in power systems. For hourly load forecasting, analyses of the capabilities and characteristics of ANN and WNN are done. The suggested strategies have already been tried and tested in actual world settings with great success.

Pore pressure is one of the main formation conditions that affects the efficiency of drilling operations and impacts its cost. Accurate prediction of the pore pressure and the parameters controlling it will help reduce the drilling cost and avoid in some cases catastrophic accidents. Many empirical models reported in the literature were used to predict the pore pressure based on either drilling parameters or log data. Empirical models require trends such as normal or abnormal pressure to predict the pore pressure. Few researchers applied artificial intelligence (AI) techniques to predict the pore pressure using one or maximum two AI methods (which are black box). There is no developed empirical correlation for pore pressure prediction based on optimized AI techniques. The objective of this paper is to predict the pore pressure based on both drilling parameters and log data, namely weight on bit (WOB), rotary speed (RPM), rate of penetration (ROP), mud weight (MW), bulk density (RHOB), porosity ( $$\phi $$ ), and compressional time ( $$\Delta {t}$$ ). Real field data will be used to predict the pore pressure using artificial neural network (ANN). Finally, for the first time, a new empirical correlation for pore pressure prediction will be developed based on the optimized ANN model. The obtained results showed that it is very important to combine the drilling parameters and the logging data to predict the pore pressure with a high accuracy. A new empirical correlation was developed using the optimized ANN method that can estimate pore pressure with high accuracy (correlation coefficient of 0.998 and average absolute percentage error of 0.17%). Unlike the published empirical models, the new model requires no prior pressure trends (such as normal or abnormal pressures) to perform prediction.

Effective seismic interpretation requires correlating seismic data with well data. This is usually accomplished by visually correlating a synthetic seismogram, generated from sonic and density logs, with nearby seismic data. If a sonic log is not available but a density log is, then Gardner’s relationship is generally used to estimate sonic data. For those situations where synthetic seismograms are derived but sonic or density log data are not available, techniques have evolved to estimate the sonic traveltime from other well log data, primarily the resistivity curve.

Albian carbonates are important oil reservoirs on the NE coast of Rio de Janeiro. In this work, aiming to evaluate the porosity of these deposits, we used basic well logs, geological information and petrophysical laboratory data from two oil fields of this region. However, proposed models to study this kind of reservoirs consider combinations of porosities derived from density and neutron logs, but do not recognize the importance of sonic porosity in the identification of fractures that distort the porosity models when they are compared with experimental data. Still, joint analysis of porosities derived from these three logs is addressed in this study and a new regression is proposed, which showed high correlation with the petrophysical data in both fields, regardless the differences of diagenetic processes that every oil field was submitted. Furthermore, the linear regression model applied to the calculation of Archie's cementation coefficient (m) demonstrated that in zones with not connected porosity the value of m will be greatly increased and should not to be considered to calculate the saturation. Finally, using porosity cross plots derived from density and sonic logs allowed to identify different kind of porosities and to visualize the effective porosity along the geological formations.

ABSTRACTP‐wave and S‐wave velocities are vital parameters for the processing of seismic data and may be useful for geotechnical studies used in mine planning if such data were collected more often. Seismic velocity data from boreholes increase the robustness and accuracy of the images obtained by relatively costly seismic surface reflection surveys. However, sonic logs are rarely acquired in boreholes in‐and‐near base metal and precious metal mineral deposits until a seismic survey is planned, and only a few new holes are typically logged because the many hundreds of holes previously drilled are no longer accessible. If there are any pre‐existing petrophysical log data, then the data are likely to consist of density, magnetic susceptibility, resistivity and natural gamma logs. Thus, it would be of great benefit to be able to predict the velocities from other data that is more readily available.In this work, we utilize fuzzy c‐means clustering to build a “fuzzy” relationship between sonic velocities and other petrophysical borehole data to predict P‐wave and S‐wave velocity. If boreholes with sonic data intersect most of the important geological units in the area of interest, then the cluster model developed may be applied to other boreholes that do not have sonic data, but do have other petrophysical data to be used for predicting the sonic logs. These predicted sonic logs may then be used to create a three‐dimensional volume of velocity with greater detail than would otherwise be created by the interpolation of measured sonic data from sparsely located holes.Our methodology was tested on a dataset from the Kevitsa Ni‐Cu‐PGE deposit in northern Finland. The dataset includes five boreholes with wireline logs of P‐wave velocity, S‐wave velocity, density, natural gamma, magnetic susceptibility and resistivity that were used for cluster analysis. The best combination of input data for the training section was chosen by trial and error, but differences in the misfit between the various training datasets were not particularly significant. Our results show that the fuzzy c‐means method can predict sonic velocities from other borehole data very well, and the fuzzy c‐means method works better than using multiple linear‐regression fitting. The predicted P‐wave velocity data are of sufficient quality to robustly add low‐frequency information for seismic impedance inversion and should provide better velocity models for accurate depth conversion of seismic reflection data.

Genetic algorithms (GAs) have been shown to apply well to optimizing the design and operations of water distribution systems (WDSs). The objective has usually been to minimize cost, subject to hydraulic constraints such as satisfying minimum pressure. More recently, the focus of optimization has expanded to include water quality concerns. This added complexity significantly increases the computational requirements of optimization. Considerable savings in computer time can be achieved by using a technique known as metamodeling. A metamodel is a surrogate or substitute for a complex simulation model. This research uses a metamodeling approach to optimize a water distribution design problem that includes water quality. The type of metamodels used are artificial neural networks (ANNs), as they are capable of approximating the nonlinear functions that govern flow and chlorine decay in a WDS. The ANNs were calibrated to provide a good approximation to the simulation model. In addition, two techniques are presented to improve the ability of metamodels to find the same optimal solution as the simulation model. Large savings in computer time occurred from training the ANNs to approximate chlorine concentrations (approximately 700 times faster than the simulation model) while still finding the optimal solution.

In recent years, machine learning algorithms have been used in the mass appraisal of real estate. In this study, 5 machine learning algorithms are used for residential type real estate. Machine learning algorithms used for mass appraisal in this study are Artificial Neural Networks (ANN), Random Forest (RO), Multiple Regression Analysis (MRA), K-Nearest Neighborhood (k-nn), Support Vector Regression (SVR). To test the study, real estate data collected from the central districts of Ankara, were used. The main purpose of this study is to find out which machine learning algorithm gives the best results for the mass appraisal of real estates and to reveal the most important variables that affect the prices of real estate. According to the results obtained for the city of Ankara, it was observed that the best algorithm for mass appraisal is RF in residential-type real estates, followed by the ANN, k-nn, and linear regression algorithms, respectively. According to the results obtained from the residential real estate, it was concluded that heating and distances to places of importance had the greatest effect on the value.

Formation pressure is a critical formation condition that affects the efficiency and the economy of drilling operations. The knowledge of the formation pressure is significant to control the well. It will assist in avoiding problems associated with drilling operation and decreasing the cost of the drilling operation. It is essential to predict formation pressure accurately prior to the drilling process to prevent circulation loss and kick. Many methods are used to estimate the formation pressure either from log information or drilling parameters. These methods need pressure trends such as abnormal or normal to estimate the formation pressure. Only two papers used artificial intelligence (AI) to estimate the formation pressure by applying only two AI techniques. In this paper, actual field measurements such as log data (formation density (RHOB), porosity (ϕ), and compressional time (Δt)) and drilling parameters (weight on bit (WOB), rotary speed (RPM), penetration rate (ROP), mud density (MW)) were utilized by five techniques of AI to predict the pore pressure. These AI techniques are artificial neural networks (ANN), radial basis function (RBF), fuzzy logic (FL), support vector machine (SVM), and functional networks (FN). In addition, comparative analyses were performed to determine the best combination of AI technique to predict the pore pressure with high accuracy. All artificial intelligence techniques predicted the formation pressure with high performance. In addition, the developed AI methods can be used to estimate the formation pressure without the need for normal pressure trends. The comparative analysis results show that support vector machine has the feature of formation pressure estimation by its short time prediction and high accuracy (a coefficient of determination of 0.995 and an average percentage error of 0.14%). It is recommended to apply SVM to predict the pore pressure in field operations.

The technique described is of utmost importance in stratigraphic interpretation because it measures sonic velocities and densities and their lateral variations. It will work on layers as thin as 40 feet. These changes can be indicative of facies changes or changes in lithology. The relative amplitudes and stacking velocities of seismic data comprise the required input to the method, however, if sonic and density logs from the area are available, this information" can be incorporated leading to greater control of the final results. The procedure requires that the shape of the propagating wavelet in the data be known and that it be a symmetric, zero-phase wavelet. The method is automated, and the end product is velocity and density information for a stacked seismic trace which is displayed similar to velocity and density logs. An iterative scheme minimizes the differences between the response of a seismic modeling system and the seismic data, based on matching amplitude ratios of the data. The method can be performed on as many stacked traces in an area as is necessary to achieve the objective of the explorationist. The technique has been applied to marine data from several different geologic provinces. When the results were compared to. sonic and density logs in the proximity of the seismic data, the correlations were good. INTRODUCTION In order to effectively use seismic data to define and evaluate potential stratigraphic traps, we must be able to detect lateral changes in velocity or some lithology-related physical parameter such as acoustic impedance. We will demonstrate two modeling methods which use the amplitude information in the data to transform seismic data into velocity or acoustic impedance logs. A related problem concerns the correlation of seismic data and well log information. The sonic and density logs give detailed information at the well which can be correlated to lithology; however, they can only measure velocity and density at the borehole. Conversely, seismic data, while lacking in the detail possessed by log data, can be used to detect and measure lateral variations in velocity. We will show methods which make seismic and well log data more correlative. We will further develop techniques for using the detailed velocity information available at the well to calibrate the logs derived from seismic data. These logs will then be used to measure velocities and their lateral variations away from the well. GENERAL SEISMIC PROCESS Figure 1 is a schematic representation of the seismic process and the role of the interpreter. In the center of the figure is a seismic trace which is the result of collecting seismic data over the subsurface depicted on the left of the figure. This operation can be expressed in terms of simple communications theory as the convolution of the earth reflection series with a propagating wavelet.

Petrophysical properties including volume of shale, porosity and water saturation are significance parameters for petroleum companies in evaluating the reservoirs and determining the hydrocarbon zones. These can be achieved through conventional petrophysical calculations from the well logs data such as gamma ray, sonic, neutron, density and deep resistivity. The well logging operations of the targeted limestone Mishrif reservoirs in Ns-X Well, Nasiriya Oilfield, south of Iraq could not be done due to some problems related to the well condition. The gamma ray log was the only recorded log through the cased borehole. Therefore, evaluating the reservoirs and estimating the perforation zones has not performed and the drilled well was abandoned. This paper presents a solution to estimate the missing open-hole logs of Mishrif Formation including sonic, neutron, density and deep resistivity using supervised Artificial Neural Network (ANN) in Petrel software (2016.2). Furthermore, the original gamma-ray log along with the predicted logs data from ANN models were processed, and the petrophysical properties including volume of shale, effective porosity and water saturation were calculated to determine the hydrocarbon zones. The ANN Mishrif Formation models recorded coefficient of determination (R2) of 0.65, 0.77, 0.82, and 0.04 between the predicted and the tested logs data with total correlations of 0.67, 0.91, 0.84 and 0.57 for sonic, neutron, density, and resistivity logs respectively. The best possible hydrocarbon-bearing zone ranges from the depth of about 1980-2030 m in the mB1unit. The ANN provides a good accuracy and data matching in clean and non-heterogeneous formations compared to those with higher heterogeneity that contain more than one type of lithology. The Ns-X Well can, therefore, be linked to the development plans of the Nasiriya Field instead of neglect it.

A review of the coals on the UK continental shelf as conventional dry gas source rocks and coalbed methane reservoirs has been undertaken using wireline log data from 1747 oil/gas wells. Coals ranging from Late Devonian to Pleistocene age were recorded, with important coal-bearing sequences in the Lower and Upper Carboniferous, Middle Jurassic and Palaeogene. The coals range from lignite to anthracite rank. Coal thicknesses were interpreted from a combination of gamma, sonic and density wireline logs. However, it is apparent that relatively large source/detector spacings and high logging speeds used in deep oil/gas wells fail to completely resolve thin coals. Frequency distributions of coal thickness for the offshore data set cover about 4720 observations in subsets based on geological age and indicate a high positive skewness with evidence of truncation at thicknesses less than approximately 2 ft (0.6 m). A sample of coal thicknesses based on 1227 observations from 66 cored boreholes in the onshore Westphalian displays similar frequency characteristics, but with the truncation confined to coals less than 1 in (0.03 m) thick. Data truncation seen in the offshore wells is attributed to incomplete wireline log resolution. At the maximum end of the distributions, the data generally display an asymptotic shape for larger thicknesses, normally somewhere in excess of 10 ft (3.0 m). To estimate the unresolved thin coals as well as test the statistical validity of the distributions, comparisons were made of the observed frequency distributions with a number of theoretical distributions of the exponential family, including the generalized Pareto distribution. In addition to this frequential approach, a series of thickness-weighted plots, indicative of coal volume, are introduced. Subsequently, conclusions are drawn regarding the estimation of the total coal resource base from this data. In particular, the effects of the truncation can be quantified and are of the order of 20–30%. These are important adjustments to the estimates of overall coal volumes which are used to assess gas-generating capacity.

The determination of the velocity of seismic waves as a function of depth at a well is generally based on the sonic log often complemented by well shooting. Thus, sonic logs in addition to their contribution to the study of the porosity of geological formations contribute to the improvement of surface seismic data and their interpretation. However, events recorded on surface seismograms are reflections while sonic logs and well surveys record arrivals of direct transmitted waves. Thus, identifications of seismic mirrors are inferred on the basis of velocity contrasts and travel times without direct experimental evidence linking the sonic log and the surface seismogram. The roles of multiple reflections and mode conversion remain hypothetical. Reflection coefficients can merely be estimated. The Vertical Seismic Profile (VSP) corresponding to a well is the seismogram which would be obtained when shooting near a well and recording the input from seismic traces regularly spaced inside the well. A VSP provides the missing direct experimental link between surface seismograms on one side and sonic logs and checks shot results on the other side. Actually, for a relatively modest additional effort invested in field operations and processing, a VSP can produce all the information contained in a normal well velocity survey and much more. VSPs may be used for the delineation of reservoirs, the identification and analysis of seismic events and thorough velocity studies where anisotropy is considered. While logs are influenced by a relatively small volume of geological formations around the well, VSPs allow studies where considered dimensions are at least those of the Fresnel Zone. Introduction A sonic log or continuous velocity log of a well indicates the transit time for acoustic waves in microseconds per foot or per meter as a function of depth. It is a very valuable document for porosity determination, moreover it reflects in great detail the stratigraphy of a sedimentary series. The quality of correlations between sonic logs obtained in wells several tens of miles apart is frequently surprisingly good. Actually, it may be said that the ultimate wish of users of seismic sections is to have them transformed into a continuous series of sonic logs. This will most probably remain a wish. Although interesting attempts are being made. Figure 1 is an example of a section where relative isovelocities are contoured. It is the result of a so-called inversion of a seismic reflection section. The well velocity log has been filtered through a band pass filter in order to remove the high and the very low frequencies which cannot be recorded through seismic channels. Thus, what is left is a plot of "relative velocities" as a function of time. Both the thin velocity anomalies and the general increase of velocities with depth are absent There is obviously a strong similarity between the filtered sonic log and the relative velocity curves deduced from the seismic traces. Strictly speaking, these curves should be considered as representing relative acoustic impedances (products of velocities by densities). Actually where density contrasts are strong and both a sonic and a density log are available, an acoustic impedance log is calculated and used. In many cases, density logs are not available and, moreover, the variations of velocities reflect accurately enough the variations of acoustic impedances.